© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17333
    Prev
    Next
    INDEX
    Explanations

    ionization and related suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤĴç«ĭãģ¦
    -0.08
    меÑģÑĤи
    -0.08
    éné
    -0.08
    äºĭçļĦ
    -0.08
    ETTI
    -0.07
    -sized
    -0.07
    çĹħæĥħåĪĨæŀIJ
    -0.07
    iels
    -0.07
    ëĭ¤ë©´
    -0.07
    ï¾ŀ
    -0.07
    POSITIVE LOGITS
    ally
    0.08
    æĪIJåħ¨
    0.07
    åĩºçļĦ
    0.07
    åĩºæĿ¥çļĦ
    0.07
    ation
    0.07
    åĩºä¾ĨçļĦ
    0.07
    abeth
    0.07
    dem
    0.07
    andre
    0.07
    液çļĦ
    0.07
    Activations Density 0.003%

    No Known Activations